Avatar

Huang Fang

Researcher

Baidu Research

Biography

I am currently a research scientist in the Cognative Computing Lab, Baidu Research. I received my Ph.D. degree in Computer Science from the University of British Columbia, where I was fortunate to be advised by Prof. Michael Friedlander. I also worked with Prof. Cho-Jui Hsieh from UCLA when I was a master student at UCDavis during 2015-2017. You can contact me by fangazq877@gmail.com or fanghuang@baidu.com.

Interests

  • Optimization
  • Learning theory
  • Data mining

Education

  • Ph.D. in Computer Science, 2021

    University of British Columbia

  • M.S. in Statistics and Computer Science, 2017

    University of California, Davis

  • B.Sc. in Financial Mathematics, 2015

    Central University of Finance and Economics (China)

Preprints

Zhenan Fan*, Huang Fang*, Michael P. Friedlander (2022). A dual approach for federated learning. (* equal contribution).

ArXiv

Zhenan Fan, Huang Fang, Zirui Zhou, Jian Pei, Michael P. Friedlander, Yong Zhang (2022). Fair and efficient contribution valuation for vertical federated learning.

ArXiv

Zhenan Fan*, Huang Fang*, Michael P. Friedlander (2021). Safe-screening rules for atomic-norm regularization. (* equal contribution). Submitted.

PDF

Publications

Shengyuan Chen, Yunfeng Cai, Huang Fang, Xiao Huang, Mingming Sun (2023). Differentiable Neuro-Symbolic Reasoning on Large-Scale Knowledge Graphs. In NeurIPS 2023.

PDF

Huang Fang, Yang Liu, Yunfeng Cai, Mingming Sun (2023). MLN4KB: an efficient Markov logic network engine for large-scale knowledge bases and structured logic rules. In WWW 2023.

PDF Code

Huang Fang, Xiaoyun Li, Chenglin Fan, Ping Li (2023). Improved Convergence of Differential Private SGD with Gradient Clipping. In ICLR 2023.

PDF

Zhenan Fan, Huang Fang, Zirui Zhou, Jian Pei, Michael P. Friedlander, Changxin Liu, Yong Zhang (2022). Improving Fairness for Data Valuation in Federated Learning. In IEEE International Conference on Data Engineerin (ICDE) 2022.

ArXiv

Huang Fang (2021). First-order methods for structured optimization. PhD Dissertation.

PDF Slides

Huang Fang, Guanhua Fang, Tan Yu, Ping Li (2021). Efficient Greedy Coordinate Descent via Variable Partitioning. In UAI 2021.

PDF

Huang Fang, Zhenan Fan, Michael P. Friedlander (2021). Fast convergence of stochastic subgradient method under interpolation. In ICLR 2021.

PDF

Huang Fang, Nicholas J. A. Harvey, Victor S. Portella, Michael P. Friedlander (2020). Online mirror descent and dual averaging: keeping pace in the dynamic case. In ICML 2020. Extended version appeared in JMLR 2022.

PDF Journal PDF

Huang Fang, Zhenan Fan, Yifan Sun, Michael P. Friedlander (2020). Greed meets sparsity: understanding and improving greedy coordinate descent for sparse optimization. In AISTATS 2020.

PDF Code

Huang Fang, Minhao Cheng, Cho-Jui Hsieh, Michael P. Friedlander (2019). Fast training for large-scale one-versus-all linear classifiers using tree-structured initialization. In SDM 2019.

PDF Code Supplements

Huang Fang, Minhao Cheng, Cho-Jui Hsieh (2017). A Hyperplane-based Algorithm for Semi-supervised Dimension Reduction. In ICDM 2017.

PDF

Huang Fang, Zhen Zhang, Yiqun Shao, Cho-Jui Hsieh (2017). Improved Bounded Matrix Completion for Large-Scale Recommender Systems. In IJCAI 2017.

PDF Code